Paraphrase Lattice for Statistical Machine Translation
Summary :
Lattice decoding in statistical machine translation (SMT) is useful in speech translation and in the translation of German because it can handle input ambiguities such as speech recognition ambiguities and German word segmentation ambiguities. In this paper, we show that lattice decoding is also useful for handling input variations. “Input variations” refers to the differences in input texts with the same meaning. Given an input sentence, we build a lattice which represents paraphrases of the input sentence. We call this a paraphrase lattice. Then, we give the paraphrase lattice as an input to a lattice decoder. The lattice decoder searches for the best path of the paraphrase lattice and outputs the best translation. Experimental results using the IWSLT dataset and the Europarl dataset show that our proposed method obtains significant gains in BLEU scores.
- Publication
- IEICE TRANSACTIONS on Information Vol.E94-D No.6 pp.1299-1305
- Publication Date
- 2011/06/01
- Publicized
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.E94.D.1299
- Type of Manuscript
- PAPER
- Category
- Natural Language Processing
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Takashi ONISHI, Masao UTIYAMA, Eiichiro SUMITA, "Paraphrase Lattice for Statistical Machine Translation" in IEICE TRANSACTIONS on Information,
vol. E94-D, no. 6, pp. 1299-1305, June 2011, doi: 10.1587/transinf.E94.D.1299.
Abstract: Lattice decoding in statistical machine translation (SMT) is useful in speech translation and in the translation of German because it can handle input ambiguities such as speech recognition ambiguities and German word segmentation ambiguities. In this paper, we show that lattice decoding is also useful for handling input variations. “Input variations” refers to the differences in input texts with the same meaning. Given an input sentence, we build a lattice which represents paraphrases of the input sentence. We call this a paraphrase lattice. Then, we give the paraphrase lattice as an input to a lattice decoder. The lattice decoder searches for the best path of the paraphrase lattice and outputs the best translation. Experimental results using the IWSLT dataset and the Europarl dataset show that our proposed method obtains significant gains in BLEU scores.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E94.D.1299/_p
Copy
@ARTICLE{e94-d_6_1299,
author={Takashi ONISHI, Masao UTIYAMA, Eiichiro SUMITA, },
journal={IEICE TRANSACTIONS on Information},
title={Paraphrase Lattice for Statistical Machine Translation},
year={2011},
volume={E94-D},
number={6},
pages={1299-1305},
abstract={Lattice decoding in statistical machine translation (SMT) is useful in speech translation and in the translation of German because it can handle input ambiguities such as speech recognition ambiguities and German word segmentation ambiguities. In this paper, we show that lattice decoding is also useful for handling input variations. “Input variations” refers to the differences in input texts with the same meaning. Given an input sentence, we build a lattice which represents paraphrases of the input sentence. We call this a paraphrase lattice. Then, we give the paraphrase lattice as an input to a lattice decoder. The lattice decoder searches for the best path of the paraphrase lattice and outputs the best translation. Experimental results using the IWSLT dataset and the Europarl dataset show that our proposed method obtains significant gains in BLEU scores.},
keywords={},
doi={10.1587/transinf.E94.D.1299},
ISSN={1745-1361},
month={June},}
Copy
TY - JOUR
TI - Paraphrase Lattice for Statistical Machine Translation
T2 - IEICE TRANSACTIONS on Information
SP - 1299
EP - 1305
AU - Takashi ONISHI
AU - Masao UTIYAMA
AU - Eiichiro SUMITA
PY - 2011
DO - 10.1587/transinf.E94.D.1299
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E94-D
IS - 6
JA - IEICE TRANSACTIONS on Information
Y1 - June 2011
AB - Lattice decoding in statistical machine translation (SMT) is useful in speech translation and in the translation of German because it can handle input ambiguities such as speech recognition ambiguities and German word segmentation ambiguities. In this paper, we show that lattice decoding is also useful for handling input variations. “Input variations” refers to the differences in input texts with the same meaning. Given an input sentence, we build a lattice which represents paraphrases of the input sentence. We call this a paraphrase lattice. Then, we give the paraphrase lattice as an input to a lattice decoder. The lattice decoder searches for the best path of the paraphrase lattice and outputs the best translation. Experimental results using the IWSLT dataset and the Europarl dataset show that our proposed method obtains significant gains in BLEU scores.
ER -
English
